FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
For medical AI, this work addresses the need for transparent, evidence-grounded reasoning by introducing step-level supervision, though it is incremental over existing RL and retrieval methods.
FaithMed improves medical LLM reasoning by combining clinician-designed rubrics with reinforcement learning, achieving +9% over agentic-search baselines and +15.5% in evidence-based medicine rubric scores across seven benchmarks.
Faithful reasoning is essential in medicine, where clinical decisions require transparent justification grounded in reliable evidence. Current medical LLMs either lack active access to evidence or use retrieved evidence without supervising how it should be appraised and applied during reasoning. To address this, we formalize evidence-based medicine principles as process-level criteria and introduce FaithMed, a framework that combines clinician-designed, automatically refined rubrics with reinforcement learning using step-level process reward assignment and advantage grouping. Across seven medical benchmarks, FaithMed improves over agentic-search baselines (+9% on average) and outcome-only RL (+5.8%), while raising average evidence-based medicine rubric scores over agentic-search Qwen3 baselines (+15.5%). This work demonstrates that explicit step-level supervision can improve both task success and the faithfulness of the reasoning process. Code is available at https://github.com/cxcscmu/FaithMed.